© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57797
    Prev
    Next
    INDEX
    Explanations

    faster than light, speed, acceleration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»ĩ
    -0.08
    ìĺģ
    -0.08
    ieme
    -0.07
    irat
    -0.07
     Shade
    -0.07
     vẹn
    -0.07
    èĮľ
    -0.07
     Ogg
    -0.07
    æ²īçĶ¸çĶ¸
    -0.07
     ehd
    -0.06
    POSITIVE LOGITS
     speeds
    0.08
    æľĢå¿«çļĦ
    0.08
    è·Įçł´
    0.07
     harmless
    0.07
     unrestricted
    0.07
    æ°´ä¸Ń
    0.07
    å¹³éĿĻ
    0.07
     дале
    0.07
    fahren
    0.07
    æ¿Ģ
    0.07
    Activations Density 0.003%

    No Known Activations